Perplexity Scraper | Answers, Citations & Brand Tracking
Pricing
from $9.00 / 1,000 prompt checked, 1 or 2 captures
Perplexity Scraper | Answers, Citations & Brand Tracking
Send prompts to Perplexity and get the full answer, every cited source in the order of its [1] [2] markers, and the pages it read. Track your domains and brands, get citation rates over 1 to 5 answers, and see what changed since your last run.
Pricing
from $9.00 / 1,000 prompt checked, 1 or 2 captures
Rating
0.0
(0)
Developer
Alexis Morain
Maintained by CommunityActor stats
0
Bookmarked
1
Total users
1
Monthly active users
4 days ago
Last modified
Features
Share
What does Perplexity Scraper do?
Perplexity Scraper sends your prompts to Perplexity (the sonar model with live web search) and returns what it answers: the full answer, every source it cites in the order of its [1], [2], [3] markers, and the search results it read. You give it prompts like best crm for startups. For each one you get a citation rate per domain and a mention rate and rank for your brands, measured over 1, 3 or 5 answers to the same prompt.
Use it to see whether Perplexity cites your site, which sites it trusts in your market, and how that moves from week to week. It works as a Perplexity API for SEO, GEO (generative engine optimization) and brand reporting. No Perplexity account, no API key of your own, no browser on your side.
It covers Perplexity only. For ChatGPT, Google AI Mode, Google AI Overviews or Gemini, see our other Actors.
Why use Perplexity Scraper?
Perplexity is the most citation-heavy AI engine we measured. On a real run of 50 prompts on November 9, 2026, from the United States, every answer cited sources, with 8.8 domains per answer on average and 10 search results read. When the question is "which sites does AI send people to", Perplexity gives the most data per answer.
It is also the most stable. We asked best crm software for startups three times in a row: the three answers cited the same 10 domains. On Perplexity, 1 capture is usually enough, so you pay for one answer, not three. Switch to 3 captures when you want proof that a citation holds.
What you get on top:
- Citation order: sources keep the order of Perplexity's numbered markers, so position 1 is the first source the answer relies on.
- Search results: the pages Perplexity read, cited or not.
- Tracked domains: citation rate and best position for your site and your competitors. A tracked domain also counts its subdomains.
- Tracked brands: how often each brand name appears in the answer, and its rank (first brand named, second, and so on).
- Compare mode: domains and brands gained or lost since the previous run, with old and new rates.
- 192 countries for the web search.
- Answers in seconds: a run of 50 prompts finished in 74 seconds.
- Scheduling, API access, webhooks and integrations (Make, Zapier, n8n, Google Sheets) from the Apify platform.
What data can Perplexity Scraper extract?
One result per prompt:
| Field | Type | Description |
|---|---|---|
prompt | string | The prompt as you wrote it |
model | string | Perplexity model that answered (sonar) |
status | string | answered or failed |
capturesSucceeded | integer | Answers received. Every rate is divided by this number |
answerText | string | Full answer in Markdown (the longest of the captures) |
citedDomains | array | Each cited domain with its captures, rate and best position |
sources | array | Each cited page: URL, title, rate, best position |
brandMentions | array | Your brands found in the answer, with rate and best rank |
trackedDomains | array | Your domains: citation rate and best position |
trackedBrands | array | Your brands: mention rate and best rank |
searchResults | array | Pages Perplexity read, with their position |
changes | object | Compare mode: gained and lost domains and brands, tracked rates before and after |
How to scrape Perplexity
- Open the Actor and type your prompts, one per line.
- Pick the country the web search runs from, for example
usorgb. - Keep 1 capture. Pick 3 or 5 only if you want to check that a citation is stable.
- Add your domain and competitor domains in Domains to track, and brand names in Brands to track.
- Switch on Compare with previous run if you plan to run it on a schedule.
- Press Start, then download the results as JSON, CSV or Excel, or read them through the API.
There is no language setting: Perplexity answers in the language of the prompt. Write the prompt in French to get a French answer.
How much does it cost to scrape Perplexity?
You pay per prompt answered, plus a start fee of $0.001 per run:
| Captures per prompt | Free plan | Bronze and above |
|---|---|---|
| 1 (snapshot) | $0.010 | $0.009 |
| 3 (rates) | $0.030 | $0.027 |
| 5 (most reliable) | $0.050 | $0.045 |
1,000 prompts with 1 capture cost $10 on the Free plan and $9 on paid plans. Platform usage is included. Perplexity costs more than our ChatGPT, Gemini and AI Mode Actors because each answer is generated live, with a full web search behind it.
A prompt is charged only when at least one answer came back. If some captures fail, the prompt is charged at the level it reached: 3 asked and 2 received is charged as 1 capture. A prompt with no answer comes back with status: failed and is not charged. The run stops before it would go over the maximum cost you set.
Free Apify plan: up to 0.15 USD of DataForSEO data per day; paid plans unlimited.
Input
See the Input tab for every option. The only required field is the list of prompts, up to 1,000 per run and 500 characters each.
{"prompts": ["best crm for startups", "best email marketing tool for ecommerce"],"countryCode": "us","capturesPerPrompt": "1","trackDomains": ["hubspot.com", "pipedrive.com"],"trackBrands": ["HubSpot", "Pipedrive"],"compareWithPreviousRun": true,"historyKey": "crm-weekly"}
Output
You can download the dataset in various formats such as JSON, HTML, CSV, or Excel. Example from a real run, shortened:
{"prompt": "best crm for beginners","engine": "perplexity","model": "sonar","countryCode": "us","status": "answered","capturesRequested": 1,"capturesSucceeded": 1,"answerText": "**HubSpot CRM** is the best overall CRM for most beginners: it has a functional free plan, intuitive contact and deal tracking...","citedDomains": [{"domain": "pcmag.com", "captures": 1, "rate": 1.0, "bestPosition": 1},{"domain": "shopify.com", "captures": 1, "rate": 1.0, "bestPosition": 3},{"domain": "pipedrive.com", "captures": 1, "rate": 1.0, "bestPosition": 4}],"searchResults": [{"domain": "pcmag.com", "url": "https://www.pcmag.com/picks/the-best-crm-software", "title": "The Best CRM Software We've Tested for 2026", "position": 1}],"trackedDomains": [{"domain": "hubspot.com", "citedCaptures": 0, "citationRate": 0.0, "bestPosition": null}],"trackedBrands": [{"brand": "HubSpot", "mentionedCaptures": 1, "mentionRate": 1.0, "bestRank": 1}],"changes": null}
This example shows why you track both: HubSpot is the first brand named, but hubspot.com is not cited. Perplexity recommends it from review sites.
changes is null on the first run of a prompt: that run becomes the baseline for the next one.
Tips
- Start with 1 capture. Perplexity repeats its sources from one answer to the next, so extra captures rarely change the rates.
- Give each client or project its own History name, so compare mode keeps their histories apart.
- Brand names are matched as whole words, case ignored. Add the spellings people use (
Zoho CRMandZoho).
FAQ, limits and support
Which Perplexity does it ask?
The sonar model with web search on, the one behind Perplexity's API. Answers are capped at about 1,000 tokens, which covers a full recommendation answer.
Why is there no language field?
Perplexity has none. It answers in the language of the prompt, and the country field sets where the web search runs.
Is it legal?
Our Actors are ethical and do not extract any private user data, such as email addresses, gender, or location. They only extract what the user has chosen to share publicly. We therefore believe that our Actors, when used for ethical purposes by Apify users, are safe. However, you should be aware that your results could contain personal data. Personal data is protected by the GDPR in the European Union and by other regulations around the world. You should not scrape personal data unless you have a legitimate reason to do so. If you're unsure whether your reason is legitimate, consult your lawyers.
Something is wrong or missing?
Open an issue in the Issues tab. To call the Actor from your own code, see the API tab.
Guide and use cases
Use cases for outbound and automation, the output fields, pricing and common questions are on the Perplexity Scraper page of my site. The AI search visibility family page puts it side by side with the other scrapers of the same family.